#
ENJA

agents-shipgate

MCP Server

ThreeMoonsLab/agents-shipgate

Agents Shipgate is a deterministic merge gate for AI-generated agent capability changes, analyzing tool sources and configurations locally without agent execution or network calls.

98 3Apache-2.0Updated 2026-08-12

Overview

Agents Shipgate acts as a static, local-first merge gate and control loop designed specifically for AI coding agents and repositories utilizing agent tools, MCP exports, OpenAPI specs, and SDK artifacts. It evaluates capability changes, checks trust roots, and produces deterministic findings, Markdown reports, JSON outputs, and SARIF files. By relying on strict cryptographic control envelopes and verification receipts, it prevents unauthorized privilege escalation or bypass of security controls during agentic development workflows.

Capabilities

  • Deterministic static analysis of AI agent tools and capability configurations
  • Support for multi-framework inputs including MCP, OpenAPI, LangChain, CrewAI, and Google ADK
  • Structured JSON and SARIF security reporting
  • Rigorous control state machine for coding agents (checking permissions, next actions, and merge authority)
  • Automated workspace bootstrapping and patch application for first-time adopters

Best for

Gating AI-generated pull requests and agent capability changes in CI/CD pipelines, Auditing MCP servers, OpenAPI specs, and agent SDK configurations for security compliance, Running local control loops before coding agents mark tasks as complete, Generating static analysis reports for AI tool definitions across LangChain, CrewAI, and OpenAI Agents SDK

Works with

Claude CodeCodexCursorGitHub CopilotOpenCode
Evoa Score breakdown= Σ (score × weight)
86
Task usefulness20%88 → +17.6

実タスクにどれだけ役立つか(機能の豊富さ・用途の明確さ)。 AIによるcapabilities/use-cases解析

Code quality15%95 → +14.3

実装・指示の品質。 AIによるSKILL.md/README解析

Maintenance15%100 → +15.0

リポジトリがどれだけ活発に保守されているか。 GitHub 最終push日時の新しさ

Documentation12%48 → +5.8

ドキュメントの充実度・分かりやすさ。 README/独自要約の情報量

Security15%100 → +15.0

危険・不審な挙動が無いか。 AIによるセキュリティレビュー

Originality10%90 → +9.0

ありふれたラッパーではない独自性。 AIによる独自性判定

Popularity8%51 → +4.1

コミュニティの採用度。 GitHub Stars/Forks(対数スケール)

Compatibility5%100 → +5.0

対応AIエージェントの広さ。 AIによる対応エージェント判定

Weighted total85.7 / 100

ライセンス不明/制限あり(Red)のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →

Security considerations

The skill enforces strict static analysis with zero network access or agent execution during scans. It prevents tampering by validating cryptographic receipts and tying control states directly to workspace HEAD and tree states.

Categories

Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.